AI-based Cleft Lip and Palate Surgical Information is Preferred by Both Plastic Surgeons and Patients in a Blind Comparison

INTRODUCTION

The application of artificial intelligence (AI) in healthcare has expanded in recent years, and these tools such as ChatGPT to generate patient-facing information have garnered particular interest. Online cleft lip and palate (CL/P) surgical information supplied by academic/professional (A/P) sources was therefore evaluated against ChatGPT regarding accuracy, comprehensiveness, and clarity.

METHODS

11 plastic and reconstructive surgeons and 29 non-medical individuals blindly compared responses written by ChatGPT or A/P sources to 30 frequently asked CL/P surgery questions. Surgeons indicated preference, determined accuracy, and scored comprehensiveness and clarity. Non-medical individuals indicated preference. Calculations of readability scores were determined using seven readability formulas. Statistical analysis of CL/P surgical online information was performed using paired t-tests.

RESULTS

Surgeons, 60.88% of the time, blindly preferred material generated by ChatGPT over A/P sources. Additionally, surgeons consistently indicated that ChatGPT-generated material was more comprehensive and had greater clarity. No significant difference was found between ChatGPT and resources provided by professional organizations in terms of accuracy. Among individuals with no medical background, ChatGPT-generated materials were preferred 60.46% of the time. For materials from both ChatGPT and A/P sources, readability scores surpassed advised levels for patient proficiency across seven readability formulas.

CONCLUSION

As the prominence of ChatGPT-based language tools rises in the healthcare space, potential applications of the tools should be assessed by experts against existing high-quality sources. Our results indicate that ChatGPT is capable of producing high-quality material in terms of accuracy, comprehensiveness, and clarity preferred by both plastic surgeons and individuals with no medical background.

Machine learning: an advancement in biochemical engineering

One of the most remarkable techniques recently introduced into the field of bioprocess engineering is machine learning. Bioprocess engineering has drawn much attention due to its vast application in different domains like biopharmaceuticals, fossil fuel alternatives, environmental remediation, and food and beverage industry, etc. However, due to their unpredictable mechanisms, they are very often challenging to optimize. Furthermore, biological systems are extremely complicated; hence, machine learning algorithms could potentially be utilized to improve and build new biotechnological processes. Gaining insight into the fundamental mathematical understanding of commonly used machine learning algorithms, including Support Vector Machine, Principal Component Analysis, Partial Least Squares and Reinforcement Learning, the present study aims to discuss various case studies related to the application of machine learning in bioprocess engineering. Recent advancements as well as challenges posed in this area along with their potential solutions are also presented.

Technical note: Visual, rapid, scintillation point dosimetry for in vivo MV photon beam radiotherapy treatments

BACKGROUND

While careful planning and pre-treatment checks are performed to ensure patient safety during external beam radiation therapy (EBRT), inevitable daily variations mean that in vivo dosimetry (IVD) is the only way to attain the true delivered dose. Several countries outside the US require daily IVD for quality assurance. However, elsewhere, the manual labor and time considerations of traditional in vivo dosimeters may be preventing frequent use of IVD in the clinic.

PURPOSE

This study expands upon previous research using plastic scintillator discs for optical dosimetry for electron therapy treatments. We present the characterization of scintillator discs for in vivo x-ray dosimetry and describe additional considerations due to geometric complexities.

METHODS

Plastic scintillator discs were coated with reflective white paint on all sides but the front surface. An anti-reflective, matte coating was applied to the transparent face to minimize specular reflection. A time-gated iCMOS camera imaged the discs under various irradiation conditions. In post-processing, background-subtracted images of the scintillators were fit with Gaussian-convolved ellipses to extract several parameters, including integral output, and observation angle.

RESULTS

Dose linearity and x-ray energy independence were observed, consistent with ideal characteristics for a dosimeter. Dose measurements exhibited less than 5% variation for incident beam angles between 0° and 75° at the anterior surface and 0-60∘ $^\circ $ at the posterior surface for exit beam dosimetry. Varying the angle between the disc surface and the camera lens did not impact the integral output for the same dose up to 55°. Past this point, up to 75°, there is a sharp falloff in response; however, a correction can be used based on the detected width of the disc. The reproducibility of the integral output for a single disc is 2%, and combined with variations from the gantry angle, we report the accuracy of the proposed scintillator disc dosimeters as ±5.4%.

CONCLUSIONS

Plastic scintillator discs have characteristics that are well-suited for in vivo optical dosimetry for x-ray radiotherapy treatments. Unlike typical point dosimeters, there is no inherent readout time delay, and an optical recording of the measurement is saved after treatment for future reference. While several factors influence the integral output for the same dose, they have been quantified here and may be corrected in post-processing.

Machine learning for antidepressant treatment selection in depression

Finding the right antidepressant for the individual patient with major depressive disorder can be a difficult endeavor and is mostly based on trial-and-error. Machine learning (ML) is a promising tool to personalize antidepressant prescription. In this review, we summarize the current evidence of ML in the selection of antidepressants and conclude that its value for clinical practice is still limited. Apart from the current focus on effectiveness, several other factors should be taken into account to make ML-based prediction models useful for clinical application.

Examining the Potential of ChatGPT on Biomedical Information Retrieval: Fact-Checking Drug-Disease Associations

Large language models (LLMs) such as ChatGPT have recently attracted significant attention due to their impressive performance on many real-world tasks. These models have also demonstrated the potential in facilitating various biomedical tasks. However, little is known of their potential in biomedical information retrieval, especially identifying drug-disease associations. This study aims to explore the potential of ChatGPT, a popular LLM, in discerning drug-disease associations. We collected 2694 true drug-disease associations and 5662 false drug-disease pairs. Our approach involved creating various prompts to instruct ChatGPT in identifying these associations. Under varying prompt designs, ChatGPT's capability to identify drug-disease associations with an accuracy of 74.6-83.5% and 96.2-97.6% for the true and false pairs, respectively. This study shows that ChatGPT has the potential in identifying drug-disease associations and may serve as a helpful tool in searching pharmacy-related information. However, the accuracy of its insights warrants comprehensive examination before its implementation in medical practice.

Accuracy of automated forensic dental age estimation lab (F-DentEst Lab) on large Malaysian dataset

When a disaster occurs, the authority must prioritise two things. First, the search and rescue of lives, and second, the identification and management of deceased individuals. However, with thousands of dead bodies to be individually identified in mass disasters, forensic teams face challenges such as long working hours resulting in a delayed identification process and a public health concern caused by the decomposition of the body. Using dental panoramic imaging, teeth have been used in forensics as a physical marker to estimate the age of an individual. Traditionally, dental age estimation has been performed manually by experts. Although the procedure is fairly simple, the large number of victims and the limited amount of time available to complete the assessment during large-scale disasters make forensic work even more challenging. The emergence of artificial intelligence (AI) in the fields of medicine and dentistry has led to the suggestion of automating the current process as an alternative to the conventional method. This study aims to test the accuracy and performance of the developed deep convolutional neural network system for age estimation in large, out-of-sample Malaysian children dataset using digital dental panoramic imaging. Forensic Dental Estimation Lab (F-DentEst Lab) is a computer application developed to perform the dental age estimation digitally. The introduction of this system is to improve the conventional method of age estimation that significantly increase the efficiency of the age estimation process based on the AI approach. A total number of one-thousand-eight-hundred-and-ninety-two digital dental panoramic images were retrospectively collected to test the F-DentEst Lab. Data training, validation, and testing have been conducted in the early stage of the development of F-DentEst Lab, where the allocation involved 80 % training and the remaining 20 % for testing. The methodology was comprised of four major steps: image preprocessing, which adheres to the inclusion criteria for panoramic dental imaging, segmentation, and classification of mandibular premolars using the Dynamic Programming-Active Contour (DP-AC) method and Deep Convolutional Neural Network (DCNN), respectively, and statistical analysis. The suggested DCNN approach underestimated chronological age with a small ME of 0.03 and 0.05 for females and males, respectively.

Transformers and large language models in healthcare: A review

With Artificial Intelligence (AI) increasingly permeating various aspects of society, including healthcare, the adoption of the Transformers neural network architecture is rapidly changing many applications. Transformer is a type of deep learning architecture initially developed to solve general-purpose Natural Language Processing (NLP) tasks and has subsequently been adapted in many fields, including healthcare. In this survey paper, we provide an overview of how this architecture has been adopted to analyze various forms of healthcare data, including clinical NLP, medical imaging, structured Electronic Health Records (EHR), social media, bio-physiological signals, biomolecular sequences. Furthermore, which have also include the articles that used the transformer architecture for generating surgical instructions and predicting adverse outcomes after surgeries under the umbrella of critical care. Under diverse settings, these models have been used for clinical diagnosis, report generation, data reconstruction, and drug/protein synthesis. Finally, we also discuss the benefits and limitations of using transformers in healthcare and examine issues such as computational cost, model interpretability, fairness, alignment with human values, ethical implications, and environmental impact.

Multiparametric MRI-Based Interpretable Radiomics Machine Learning Model Differentiates Medulloblastoma and Ependymoma in Children: A Two-Center Study

RATIONALE AND OBJECTIVES

Medulloblastoma (MB) and Ependymoma (EM) in children, share similarities in age group, tumor location, and clinical presentation. Distinguishing between them through clinical diagnosis is challenging. This study aims to explore the effectiveness of using radiomics and machine learning on multiparametric magnetic resonance imaging (MRI) to differentiate between MB and EM and validate its diagnostic ability with an external set.

MATERIALS AND METHODS

Axial T2 weighted image (T2WI) and contrast-enhanced T1weighted image (CE-T1WI) MRI sequences of 135 patients from two centers were collected as train/test sets. Volume of interest (VOI) was manually delineated by an experienced neuroradiologist, supervised by a senior. Feature selection analysis and the least absolute shrinkage and selection operator (LASSO) algorithm identified valuable features, and Shapley additive explanations (SHAP) evaluated their significance. Five machine-learning classifiers-extreme gradient boosting (XGBoost), Bernoulli naive Bayes (Bernoulli NB), Logistic Regression (LR), support vector machine (SVM), linear support vector machine (Linear SVC) classifiers were built based on T2WI (T2 model), CE-T1WI (T1 model), and T1 + T2WI (T1 + T2 model). A human expert diagnosis was developed and corrected by senior radiologists. External validation was performed at Sun Yat-Sen University Cancer Center.

RESULTS

31 valuable features were extracted from T2WI and CE-T1WI. XGBoost demonstrated the highest performance with an area under the curve (AUC) of 0.92 on the test set and maintained an AUC of 0.80 during external validation. For the T1 model, XGBoost achieved the highest AUC of 0.85 on the test set and the highest accuracy of 0.71 on the external validation set. In the T2 model, XGBoost achieved the highest AUC of 0.86 on the test set and the highest accuracy of 0.82 on the external validation set. The human expert diagnosis had an AUC of 0.66 on the test set and 0.69 on the external validation set. The integrated T1 + T2 model achieved an AUC of 0.92 on the test set, 0.80 on the external validation set, achieved the best performance. Overall, XGBoost consistently outperformed in different classification models.

CONCLUSION

The combination of radiomics and machine learning on multiparametric MRI effectively distinguishes between MB and EM in childhood, surpassing human expert diagnosis in training and testing sets.

Artificial Intelligence in Perioperative Care: Opportunities and Challenges

Artificial intelligence (AI) applications have great potential to enhance perioperative care. This paper explores promising areas for AI in anesthesiology; expertise, stakeholders, and infrastructure for development; and barriers and challenges to implementation.

Current applications of artificial intelligence in assisted reproductive technologies through the perspective of a patient's journey

PURPOSE OF REVIEW

This review highlights the timely relevance of artificial intelligence in enhancing assisted reproductive technologies (ARTs), particularly in-vitro fertilization (IVF). It underscores artificial intelligence's potential in revolutionizing patient outcomes and operational efficiency by addressing challenges in fertility diagnoses and procedures.

RECENT FINDINGS

Recent advancements in artificial intelligence, including machine learning and predictive modeling, are making significant strides in optimizing IVF processes such as medication dosing, scheduling, and embryological assessments. Innovations include artificial intelligence augmented diagnostic testing, predictive modeling for treatment outcomes, scheduling optimization, dosing and protocol selection, follicular and hormone monitoring, trigger timing, and improved embryo selection. These developments promise to refine treatment approaches, enhance patient engagement, and increase the accuracy and scalability of fertility treatments.

SUMMARY

The integration of artificial intelligence into reproductive medicine offers profound implications for clinical practice and research. By facilitating personalized treatment plans, standardizing procedures, and improving the efficiency of fertility clinics, artificial intelligence technologies pave the way for value-based, accessible, and efficient fertility services. Despite the promise, the full potential of artificial intelligence in ART will require ongoing validation and ethical considerations to ensure equitable and effective implementation.

Exploring the discrepancies between clinical trials and real-world data: A small-cell lung cancer study

The potential of real-world data to inform clinical trial design and supplement control arms has gained much interest in recent years. The most common approach relies on reproducing control arm outcomes by matching real-world patient cohorts to clinical trial baseline populations. However, recent studies pointed out that there is a lack of replicability, generalisability, and consensus. In this article, we propose a novel approach that aims to explore and examine these discrepancies by concomitantly investigating the impact of selection criteria and operations on the measurements of outcomes from the patient data. We tested the approach on a dataset consisting of small-cell lung cancer patients receiving platinum-based chemotherapy regimens from a real-world data cohort (n = 223) and six clinical trial control arms (n = 1224). The results showed that the discrepancy between real-world and clinical trial data potentially depends on differences in both patient populations and operational conditions (e.g., frequency of assessments, and censoring), for which further investigation is required. Discovering and accounting for confounders, including hidden effects of differences in operations related to the treatment process and clinical trial study protocol, would potentially allow for improved translation between clinical trials and real-world data. Continued development of the method presented here to systematically explore and account for these differences could pave the way for transferring learning across clinical studies and developing mutual translation between the real-world and clinical trials to inform clinical study design.

Microinstrumentation for Brain Organoids

Brain organoids are three-dimensional aggregates of self-organized differentiated stem cells that mimic the structure and function of human brain regions. Organoids bridge the gaps between conventional drug screening models such as planar mammalian cell culture, animal studies, and clinical trials. They can revolutionize the fields of developmental biology, neuroscience, toxicology, and computer engineering. Conventional microinstrumentation for conventional cellular engineering, such as planar microfluidic chips; microelectrode arrays (MEAs); and optical, magnetic, and acoustic techniques, has limitations when applied to three-dimensional (3D) organoids, primarily due to their limits with inherently two-dimensional geometry and interfacing. Hence, there is an urgent need to develop new instrumentation compatible with live cell culture techniques and with scalable 3D formats relevant to organoids. This review discusses conventional planar approaches and emerging 3D microinstrumentation necessary for advanced organoid-machine interfaces. Specifically, this article surveys recently developed microinstrumentation, including 3D printed and curved microfluidics, 3D and fast-scan optical techniques, buckling and self-folding MEAs, 3D interfaces for electrochemical measurements, and 3D spatially controllable magnetic and acoustic technologies relevant to two-way information transfer with brain organoids. This article highlights key challenges that must be addressed for robust organoid culture and reliable 3D spatiotemporal information transfer.

On inductive biases for the robust and interpretable prediction of drug concentrations using deep compartment models

Conventional pharmacokinetic (PK) models contain several useful inductive biases guiding model convergence to more realistic predictions of drug concentrations. Implementing similar biases in standard neural networks can be challenging, but might be fundamental for model robustness and predictive performance. In this study, we build on the deep compartment model (DCM) architecture by introducing constraints that guide the model to explore more physiologically realistic solutions. Using a simulation study, we show that constraints improve robustness in sparse data settings. Additionally, predicted concentration-time curves took on more realistic shapes compared to unconstrained models. Next, we propose the use of multi-branch networks, where each covariate can be connected to specific PK parameters, to reduce the propensity of models to learn spurious effects. Another benefit of this architecture is that covariate effects are isolated, enabling model interpretability through the visualization of learned functions. We show that all models were sensitive to learning false effects when trained in the presence of unimportant covariates, indicating the importance of selecting an appropriate set of covariates to link to the PK parameters. Finally, we compared the predictive performance of the constrained models to previous relevant population PK models on a real-world data set of 69 haemophilia A patients. Here, constrained models obtained higher accuracy compared to the standard DCM, with the multi-branch network outperforming previous PK models. We conclude that physiological-based constraints can improve model robustness. We describe an interpretable architecture which aids model trust, which will be key for the adoption of machine learning-based models in clinical practice.

Dr. Google vs. Dr. ChatGPT: Exploring the Use of Artificial Intelligence in Ophthalmology by Comparing the Accuracy, Safety, and Readability of Responses to Frequently Asked Patient Questions Regarding Cataracts and Cataract Surgery

PURPOSE

Patients are using online search modalities to learn about their eye health. While Google remains the most popular search engine, the use of large language models (LLMs) like ChatGPT has increased. Cataract surgery is the most common surgical procedure in the US, and there is limited data on the quality of online information that populates after searches related to cataract surgery on search engines such as Google and LLM platforms such as ChatGPT. We identified the most common patient frequently asked questions (FAQs) about cataracts and cataract surgery and evaluated the accuracy, safety, and readability of the answers to these questions provided by both Google and ChatGPT. We demonstrated the utility of ChatGPT in writing notes and creating patient education materials.

METHODS

The top 20 FAQs related to cataracts and cataract surgery were recorded from Google. Responses to the questions provided by Google and ChatGPT were evaluated by a panel of ophthalmologists for accuracy and safety. Evaluators were also asked to distinguish between Google and LLM chatbot answers. Five validated readability indices were used to assess the readability of responses. ChatGPT was instructed to generate operative notes, post-operative instructions, and customizable patient education materials according to specific readability criteria.

RESULTS

Responses to 20 patient FAQs generated by ChatGPT were significantly longer and written at a higher reading level than responses provided by Google (p < .001), with an average grade level of 14.8 (college level). Expert reviewers were correctly able to distinguish between a human-reviewed and chatbot generated response an average of 31% of the time. Google answers contained incorrect or inappropriate material 27% of the time, compared with 6% of LLM generated answers (p < .001). When expert reviewers were asked to compare the responses directly, chatbot responses were favored (66%).

CONCLUSIONS

When comparing the responses to patients' cataract FAQs provided by ChatGPT and Google, practicing ophthalmologists overwhelming preferred ChatGPT responses. LLM chatbot responses were less likely to contain inaccurate information. ChatGPT represents a viable information source for eye health for patients with higher health literacy. ChatGPT may also be used by ophthalmologists to create customizable patient education materials for patients with varying health literacy.

The Promise and Potential of Brain Organoids

Brain organoids are 3D in vitro culture systems derived from human pluripotent stem cells that self-organize to model features of the (developing) human brain. This review examines the techniques behind organoid generation, their current and potential applications, and future directions for the field. Brain organoids possess complex architecture containing various neural cell types, synapses, and myelination. They have been utilized for toxicology testing, disease modeling, infection studies, personalized medicine, and gene-environment interaction studies. An emerging concept termed Organoid Intelligence (OI) combines organoids with artificial intelligence systems to generate learning and memory, with the goals of modeling cognition and enabling biological computing applications. Brain organoids allow neuroscience studies not previously achievable with traditional techniques, and have the potential to transform disease modeling, drug development, and the understanding of human brain development and disorders. The aspirational vision of OI parallels the origins of artificial intelligence, and efforts are underway to map a roadmap toward its realization. In summary, brain organoids constitute a disruptive technology that is rapidly advancing and gaining traction across multiple disciplines.

Imaging diagnostics of pulmonary ground-glass nodules: a narrative review with current status and future directions

Background and Objective

The incidence rate of lung cancer, which also has the highest mortality rates for both men and women worldwide, is increasing globally. Due to advancements in imaging technology and the growing inclination of individuals to undergo screening, the detection rate of ground-glass nodules (GGNs) has surged rapidly. Currently, artificial intelligence (AI) methods for data analysis and interpretation, image processing, illness diagnosis, and lesion prediction offer a novel perspective on the diagnosis of GGNs. This article aimed to examine how to detect malignant lesions as early as possible and improve clinical diagnostic and treatment decisions by identifying benign and malignant lesions using imaging data. It also aimed to describe the use of computed tomography (CT)-guided biopsies and highlight developments in AI techniques in this area.

Methods

We used PubMed, Elsevier ScienceDirect, Springer Database, and Google Scholar to search for information relevant to the article's topic. We gathered, examined, and interpreted relevant imaging resources from the Second Affiliated Hospital of Nanchang University's Imaging Center. Additionally, we used Adobe Illustrator 2020 to process all the figures.

Key Content and Findings

We examined the common signs of GGNs, elucidated the relationship between these signs and the identification of benign and malignant lesions, and then described the application of AI in image segmentation, automatic classification, and the invasiveness prediction of GGNs over the last three years, including its limitations and outlook. We also discussed the necessity of conducting biopsies of persistent pure GGNs.

Conclusions

A variety of imaging features can be combined to improve the diagnosis of benign and malignant GGNs. The use of CT-guided puncture biopsy to clarify the nature of lesions should be considered with caution. The development of new AI tools brings new possibilities and hope to improving the ability of imaging physicians to analyze GGN images and achieving accurate diagnosis.

An in-silico study on the mechanical behavior of colorectal cancer cell lines in the micropipette aspiration process

Cancer alters the structural integrity and morphology of cells. Consequently, the cell function is overshadowed. In this study, the micropipette aspiration process is computationally modeled to predict the mechanical behavior of the colorectal cancer cells. The intended cancer cells are modeled as an incompressible Neo-Hookean visco-hyperelastic material. Also, the micropipette is assumed to be rigid with no deformation. The proposed model is validated with an in-vitro study. To capture the equilibrium and time-dependent behaviors of cells, ramp, and creep tests are respectively performed using the finite element method. Through the simulations, the effects of the micropipette geometry and the aspiration pressure on the colorectal cancer cell lines are investigated. Our findings indicate that, as the inner radius of the micropipette increases, despite the increase in deformation rate and aspirated length, the time to reach the equilibrium state increases. Nevertheless, it is obvious that increasing the tip curvature radius has a small effect on the change of the aspirated length. But, due to the decrease in the stress concentration, it drastically reduces the equilibrium time and increases the deformation rate significantly. Interestingly, our results demonstrate that increasing the aspiration pressure somehow causes the cell stiffening, thereby reducing the upward trend of deformation rate, equilibrium time, and aspirated length. Our findings provide valuable insights for researchers in cell therapy and cancer treatment and can aid in developing more precise microfluidic.

GloCAB cropland field boundary dataset

This dataset consists of 190,832 manually-digitized cropland field boundaries, with associated attributes, within Brazil, Ukraine, United States of America, Canada, and Russia. Specifically, 22 regions of various sizes (74km2 - 38,000km2) spanning 5 countries were digitized over a range of predominant crop types over different time periods. These field boundaries were drawn over 20 m Sentinel-2 imagery. This field boundary dataset is a byproduct of a larger effort to map cropland burned area (Global Cropland Area Burned: GloCAB product [1]), however, it has several benefits beyond its original intent, including as a training dataset for machine-learning field size analyses, or a dataset to derive cropland field characteristics across different predominant crop types and geographies.

Decolonizing global AI governance: assessment of the state of decolonized AI governance in Sub-Saharan Africa

Global artificial intelligence (AI) governance must prioritize equity, embrace a decolonial mindset, and provide the Global South countries the authority to spearhead solution creation. Decolonization is crucial for dismantling Western-centric cognitive frameworks and mitigating biases. Integrating a decolonial approach to AI governance involves recognizing persistent colonial repercussions, leading to biases in AI solutions and disparities in AI access based on gender, race, geography, income and societal factors. This paradigm shift necessitates deliberate efforts to deconstruct imperial structures governing knowledge production, perpetuating global unequal resource access and biases. This research evaluates Sub-Saharan African progress in AI governance decolonization, focusing on indicators like AI governance institutions, national strategies, sovereignty prioritization, data protection regulations, and adherence to local data usage requirements. Results show limited progress, with only Rwanda notably responsive to decolonization among the ten countries evaluated; 80% are 'decolonization-aware', and one is 'decolonization-blind'. The paper provides a detailed analysis of each nation, offering recommendations for fostering decolonization, including stakeholder involvement, addressing inequalities, promoting ethical AI, supporting local innovation, building regional partnerships, capacity building, public awareness, and inclusive governance. This paper contributes to elucidating the challenges and opportunities associated with decolonization in SSA countries, thereby enriching the ongoing discourse on global AI governance.

Imaging Analytics using Artificial Intelligence in Oncology: A Comprehensive Review

The present era has seen a surge in artificial intelligence-related research in oncology, mainly using deep learning, because of powerful computer hardware, improved algorithms and the availability of large amounts of data from open-source domains and the use of transfer learning. Here we discuss the multifaceted role of deep learning in cancer care, ranging from risk stratification, the screening and diagnosis of cancer, to the prediction of genomic mutations, treatment response and survival outcome prediction, through the use of convolutional neural networks. Another role of artificial intelligence is in the generation of automated radiology reports, which is a boon in high-volume centres to minimise report turnaround time. Although a validated and deployable deep-learning model for clinical use is still in its infancy, there is ongoing research to overcome the barriers for its universal implementation and we also delve into this aspect. We also briefly describe the role of radiomics in oncoimaging. Artificial intelligence can provide answers pertaining to cancer management at baseline imaging, saving cost and time. Imaging biobanks, which are repositories of anonymised images, are also briefly described. We also discuss the commercialisation and ethical issues pertaining to artificial intelligence. The latest generation generalist artificial intelligence model is also briefly described at the end of the article. We believe this article will not only enrich knowledge, but also promote research acumen in the minds of readers to take oncoimaging to another level using artificial intelligence and also work towards clinical translation of such research.

Human vs machine: identifying ChatGPT-generated abstracts in Gynecology and Urogynecology

BACKGROUND

ChatGPT, a publicly available artificial intelligence large language model, has allowed for sophisticated artificial intelligence technology on demand. Indeed, use of ChatGPT has already begun to make its way into medical research. However, the medical community has yet to understand the capabilities and ethical considerations of artificial intelligence within this context, and unknowns exist regarding ChatGPT's writing abilities, accuracy, and implications for authorship.

OBJECTIVE

We hypothesize that human reviewers and artificial intelligence detection software differ in their ability to correctly identify original published abstracts and artificial intelligence-written abstracts in the subjects of Gynecology and Urogynecology. We also suspect that concrete differences in writing errors, readability, and perceived writing quality exist between original and artificial intelligence-generated text.

STUDY DESIGN

Twenty-five articles published in high-impact medical journals and a collection of Gynecology and Urogynecology journals were selected. ChatGPT was prompted to write 25 corresponding artificial intelligence-generated abstracts, providing the abstract title, journal-dictated abstract requirements, and select original results. The original and artificial intelligence-generated abstracts were reviewed by blinded Gynecology and Urogynecology faculty and fellows to identify the writing as original or artificial intelligence-generated. All abstracts were analyzed by publicly available artificial intelligence detection software GPTZero, Originality, and Copyleaks, and were assessed for writing errors and quality by artificial intelligence writing assistant Grammarly.

RESULTS

A total of 157 reviews of 25 original and 25 artificial intelligence-generated abstracts were conducted by 26 faculty and 4 fellows; 57% of original abstracts and 42.3% of artificial intelligence-generated abstracts were correctly identified, yielding an average accuracy of 49.7% across all abstracts. All 3 artificial intelligence detectors rated the original abstracts as less likely to be artificial intelligence-written than the ChatGPT-generated abstracts (GPTZero, 5.8% vs 73.3%; P<.001; Originality, 10.9% vs 98.1%; P<.001; Copyleaks, 18.6% vs 58.2%; P<.001). The performance of the 3 artificial intelligence detection software differed when analyzing all abstracts (P=.03), original abstracts (P<.001), and artificial intelligence-generated abstracts (P<.001). Grammarly text analysis identified more writing issues and correctness errors in original than in artificial intelligence abstracts, including lower Grammarly score reflective of poorer writing quality (82.3 vs 88.1; P=.006), more total writing issues (19.2 vs 12.8; P<.001), critical issues (5.4 vs 1.3; P<.001), confusing words (0.8 vs 0.1; P=.006), misspelled words (1.7 vs 0.6; P=.02), incorrect determiner use (1.2 vs 0.2; P=.002), and comma misuse (0.3 vs 0.0; P=.005).

CONCLUSION

Human reviewers are unable to detect the subtle differences between human and ChatGPT-generated scientific writing because of artificial intelligence's ability to generate tremendously realistic text. Artificial intelligence detection software improves the identification of artificial intelligence-generated writing, but still lacks complete accuracy and requires programmatic improvements to achieve optimal detection. Given that reviewers and editors may be unable to reliably detect artificial intelligence-generated texts, clear guidelines for reporting artificial intelligence use by authors and implementing artificial intelligence detection software in the review process will need to be established as artificial intelligence chatbots gain more widespread use.

Integrative bioinformatics analysis to identify ferroptosis-related genes in non-obstructive azoospermia

PURPOSE

The objective of this study was to discern ferroptosis-related genes (FRGs) linked to non-obstructive azoospermia and investigate the associated molecular mechanisms.

METHOD

A dataset related to azoospermia was retrieved from the Gene Expression Omnibus database, and FRGs were sourced from GeneCards. Ferroptosis-related differentially expressed genes (FRDEGs) were discerned. Subsequently, these genes underwent analyses encompassing Gene Ontology and Kyoto Encyclopedia of Genes and Genomes, as well as protein-protein interaction (PPI) networks and assessments of functional similarity. Following the identification of hub genes, an exploration of immune infiltration, single-cell expression, diagnostic utility, and interactions involving hub genes, RNA-binding proteins (RBPs), transcription factors (TFs), microRNAs (miRNAs), and drugs was conducted.

RESULTS

A total of 35 differentially expressed FRGs were discerned. These genes demonstrated enrichment in functions and pathways associated with ferroptosis. From the PPI network, eight hub genes were selected. Functional similarity analysis highlighted the potential pivotal roles of HMOX1 and GPX4 in azoospermia. Analysis of immune cell infiltration indicated a significant decrease in activated dendritic cells in the azoospermia group, with notable correlations between hub genes, particularly SAT1 and HMGCR, and immune cell infiltration. Unique expression patterns of hub genes across various cell types in the human testis were observed, with GPX4 prominently enriched in spermatid/sperm. Eight hub genes exhibited robust diagnostic value (AUC > 0.75). Lastly, a comprehensive hub gene-miRNA-TF-RBP-drug network was constructed.

CONCLUSION

In summary, our investigation unveiled eight FRDEGs associated with azoospermia, which hold potential as biomarkers for the diagnosis and treatment of azoospermia.

Can digital leadership transform AI anxiety and attitude in nurses?

BACKGROUND

The lack of artificial intelligence applications in nursing education and the nursing profession in Turkey and the need for strategies for integrating artificial intelligence into the nursing profession continues. At this point, there is a need to transform the negative attitudes and anxiety that may occur in nurses.

OBJECTIVES

It was aimed to reorganize the professional transformation in this parallel by analyzing the effect of digital leadership perception, which is explained as how nurses approach digital technologies and innovations and their awareness of how and with which methods they can use these technologies on artificial intelligence anxiety and attitude in the nursing profession.

DESIGN

The study was designed as descriptive, correlational, and cross-sectional.

PARTICIPANTS

The research was conducted by reaching 439 nurses working in hospitals operating in three different regions of Turkey by simple random sampling method.

METHODS

In the first part of the data collection tool used in this study, digital leadership scale, artificial intelligence use anxiety, and artificial intelligence attitude scales were used, including questions determining the demographic information of nurses, their relationship with technology, artificial intelligence usage status and its importance in the profession.

RESULTS

It was determined that 29.8% of the nurses had a good relationship with technology, 66.3% knew about using artificial intelligence in health, and 27.3% wanted it to be more involved in their lives. It was determined that nurses' perceptions of digital leadership were at a medium level of 46.9% and a high level of 41.7%, 82.7% had a positive attitude towards artificial intelligence, and 82.7% had low or medium level anxiety when their artificial intelligence anxiety status was examined. There was a significant and negative relationship between digital leadership and AI anxiety (r = -0.434; p < 0.01), a significant and positive relationship between digital leadership and AI attitude (r = 0.468; p < 0.01), and a significant and negative relationship between AI attitude and AI anxiety (r = -0.629; p < 0.01). Finally, it was determined that nurses' perception of digital leadership indirectly affected AI anxiety through AI attitude (β = -0.230, 95% CI [-0.298, -0.165]).

CONCLUSION

It is suggested that the anxiety and attitude towards artificial intelligence can be transformed positively with the effect of digital leadership, and in this parallel, the digital leadership phenomenon should be evaluated as a practical implementation strategy in integrating artificial intelligence into the nursing profession.

CLINICAL RELEVANCE

Our study showed that artificial intelligence attitude has a mediating role in the indirect effect of the perception of digital leadership in nursing on AI anxiety. It was determined that nurses' digital leadership perception, artificial intelligence anxiety, and artificial intelligence attitude differed significantly with demographic variables.

Evaluating the competency of ChatGPT in MRCP Part 1 and a systematic literature review of its capabilities in postgraduate medical assessments

OBJECTIVES

As a large language model (LLM) trained on a large data set, ChatGPT can perform a wide array of tasks without additional training. We evaluated the performance of ChatGPT on postgraduate UK medical examinations through a systematic literature review of ChatGPT's performance in UK postgraduate medical assessments and its performance on Member of Royal College of Physicians (MRCP) Part 1 examination.

METHODS

Medline, Embase and Cochrane databases were searched. Articles discussing the performance of ChatGPT in UK postgraduate medical examinations were included in the systematic review. Information was extracted on exam performance including percentage scores and pass/fail rates. MRCP UK Part 1 sample paper questions were inserted into ChatGPT-3.5 and -4 four times each and the scores marked against the correct answers provided.

RESULTS

12 studies were ultimately included in the systematic literature review. ChatGPT-3.5 scored 66.4% and ChatGPT-4 scored 84.8% on MRCP Part 1 sample paper, which is 4.4% and 22.8% above the historical pass mark respectively. Both ChatGPT-3.5 and -4 performance was significantly above the historical pass mark for MRCP Part 1, indicating they would likely pass this examination. ChatGPT-3.5 failed eight out of nine postgraduate exams it performed with an average percentage of 5.0% below the pass mark. ChatGPT-4 passed nine out of eleven postgraduate exams it performed with an average percentage of 13.56% above the pass mark. ChatGPT-4 performance was significantly better than ChatGPT-3.5 in all examinations that both models were tested on.

CONCLUSION

ChatGPT-4 performed at above passing level for the majority of UK postgraduate medical examinations it was tested on. ChatGPT is prone to hallucinations, fabrications and reduced explanation accuracy which could limit its potential as a learning tool. The potential for these errors is an inherent part of LLMs and may always be a limitation for medical applications of ChatGPT.

'Let me recommend… ': use of digital nudges or recommender systems for overweight and obesity prevention-a scoping review protocol

INTRODUCTION

Recommender systems, digital tools providing recommendations, and digital nudges increasingly affect our lives. The combination of digital nudges and recommender systems is very attractive for its application in preventing overweight and obesity. However, linking recommender systems with personalised digital nudges has a potential yet to be fully exploited. Therefore, this study aims to conduct a scoping review to identify which digital nudges or recommender systems or their combinations have been used in obesity prevention and to map these systems according to the target population, health behaviour, system classification (eg, mechanisms for developing recommendations, delivery channels, personalisation, interconnection, used combination), and system implementation.

METHODS AND ANALYSIS

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guideline was used to inform protocol development. The eligibility criteria are based on the PCC framework (Population: any human; Concept: recommender systems or digital nudges; Context: obesity prevention). MEDLINE, PsycINFO, Web of Science, CINHAL, Scopus, ACM Digital Library and IEEE Xplore were searched until September 2023. Primary studies with any design published in peer-reviewed academic journals and peer-reviewed conference papers will be included. Data will be extracted into a pre-developed extraction sheet. Results will be synthesised descriptively and narratively.

ETHICS AND DISSEMINATION

No ethical approval is required for the scoping review, as data will be obtained from publicly available sources. The results of this scoping review will be published in a peer-reviewed journal, presented at conferences and used to inform the co-creation process and intervention adaptation in the context of a HealthyW8 project (www.healthyw8.eu).

Estimating the use of ChatGPT in dental research publications

INTRODUCTION

Generative artificial intelligence (GenAI) Large-language models such as ChatGPT have become increasingly popular in various fields. However, the impact of ChatGPT on dental research writing has yet to be quantified. This study aimed to assess ChatGPT's usage in dental research writing and discuss potential advantages and challenges.

METHODS

Using a bibliometric design, we performed a keyword analysis of specific 'signaling words' indicative of ChatGPT use in the titles/abstracts of 299,695 dental research abstracts indexed PubMed 2018-2024. Statistical comparisons using normalized ratios per 10,000 dental publications compared changes in word frequency before and after the ChatGPT release on November 30, 2022.

RESULTS

Before ChatGPT's release, the frequency of abstracts with signaling words was 47.1 per 10,000 papers. After the release, this increased to 224.2 per 10,000 papers, an increase of 177.2 per 10,000 papers (p = 0.014, 95 % CI 53.5-300.7). The word 'delve' showed the most significant usage increase (increased ratio=17.0).

CONCLUSIONS

This study is among the first to systematically assess the use of GenAI, specifically ChatGPT, in dental research. We found evidence of the use and growth of ChatGPT in dental research publications. This trend indicates the widespread adoption of GenAI-assisted writing in scientific communication, consistent with other scientific fields. While GenAI can potentially increase productivity and inclusivity, it raises concerns such as bias, inaccuracy, and distortion of academic incentives. Therefore, our findings support the need for clear AI guidelines and standards for academic publishing to ensure responsible use and maintain scientific integrity.

Models for depression recognition and efficacy assessment based on clinical and sequencing data

Major depression is a complex psychiatric disorder that includes genetic, neurological, and cognitive factors. Early detection and intervention can prevent progression, and help select the best treatment. Traditional clinical diagnosis tends to be subjective and misdiagnosed. Based on this, this study leverages clinical scale assessments and sequencing data to construct disease prediction models. Firstly, data undergoes preprocessing involving normalization and other requisite procedures. Feature engineering is then applied to curate subsets of features, culminating in the construction of a model through the implementation of machine learning and deep learning algorithms. In this study, 18 features with significant differences between patients and healthy controls were selected. The depression recognition model was constructed by deep learning with an accuracy of 87.26 % and an AUC of 91.56 %, which can effectively distinguish patients with depression from healthy controls. In addition, 33 features selected by recursive feature elimination method were used to construct a prognostic effect model of patients after 2 weeks of treatment, with an accuracy of 75.94 % and an AUC of 83.33 %. The results show that the deep learning algorithm based on clinical and sequencing data has good accuracy and provides an objective and accurate method for the diagnosis and pharmacodynamic prediction of depression. Furthermore, the selected differential features can serve as candidate biomarkers to provide valuable clues for diagnosis and efficacy prediction.

Behavioral intentions of university teachers and students toward the adoption of the hyb-blended learning method: Evidence from Bangladesh

Hyb-blended learning is a novel method that can serve as a substitute for conventional classroom-based learning activities, demonstrating effectiveness in both pandemics like COVID-19 and other crises, as well as in non-pandemic situations. The successful application of this method in the field of education depends on the users' intentions to adopt it. Therefore, this study aims to understand the behavioral intentions of teachers and students at Bangladeshi universities toward the adoption of the hyb-blended learning method. A correlational, cross-sectional, and sample survey-based research design was employed. Two structured questionnaires, one for teachers and one for students, were used to collect data from 171 teachers and 713 students from 11 public and 8 private universities in Bangladesh. The conceptual model of the study was developed on the theoretical underpinnings of the "Unified Theory of Acceptance and Use of Technology (UTAUT)." The study used a structural equation modeling technique to test the hypotheses. The results of the study revealed that the proposed learning method would increase teaching and learning opportunities for both teachers and students in Bangladeshi universities. They would adopt this method without relying on the experiences of others or what others think or say. Unlike teachers, the study also found that students would use it if they received support and influence from friends, fellow students, university authorities, and other external factors. However, their intentions toward adopting this method depend on the availability of resources and support for adopting it, as well as adequate and necessary understanding and talent to use it effectively. Results also revealed that they would adopt the method if it was found to be simple to use. The study has a notable practical implication, as it has proposed an alternative learning and teaching method that would be effective in Bangladeshi universities during the COVID-19 pandemic or other crises and in non-pandemic situations as well.

Evaluation of a Musculoskeletal Digital Assessment Routing Tool (DART): Crossover Noninferiority Randomized Pilot Trial

BACKGROUND

Musculoskeletal conditions account for 16% of global disability, resulting in a negative effect on patients and increasing demand for health care use. Triage directing patients to appropriate level intervention improving health outcomes and efficiency has been prioritized. We developed a musculoskeletal digital assessment routing tool (DART) mobile health (mHealth) system, which requires evaluation prior to implementation. Such innovations are rarely rigorously tested in clinical trials-considered the gold standard for evaluating safety and efficacy. This pilot study is a precursor to a trial assessing DART performance with a physiotherapist-led triage assessment.

OBJECTIVE

The study aims to evaluate trial design, assess procedures, and collect exploratory data to establish the feasibility of delivering an adequately powered, definitive randomized trial, assessing DART safety and efficacy in an NHS primary care setting.

METHODS

A crossover, noninferiority pilot trial using an integrated knowledge translation approach within a National Health Service England primary care setting. Participants were patients seeking assessment for a musculoskeletal condition, completing a DART assessment and the history-taking element of a face-to-face physiotherapist-led triage in a randomized order. The primary outcome was agreement between DART and physiotherapist triage recommendation. Data allowed analysis of participant recruitment and retention, randomization, blinding, study burden, and potential barriers to intervention delivery. Participant satisfaction was measured using the System Usability Scale.

RESULTS

Over 8 weeks, 129 patients were invited to participate. Of these, 92% (119/129) proceeded to eligibility assessment, with 60% (78/129) meeting the inclusion criteria and being randomized into each intervention arm (39/39). There were no dropouts and data were analyzed for all 78 participants. Agreement between physiotherapist and DART across all participants and all primary triage outcomes was 41% (32/78; 95% CI 22-45), intraclass correlation coefficient 0.37 (95% CI 0.16-0.55), indicating that the reliability of DART was poor to moderate. Feedback from the clinical service team led to an adjusted analysis yielding of 78% (61/78; 95% CI 47-78) and an intraclass correlation coefficient of 0.57 (95% CI 0.40-0.70). Participant satisfaction was measured quantitively using amalgamated System Usability Scale scores (n=78; mean score 84.0; 90% CI +2.94 to -2.94), equating to an "excellent" system. There were no study incidents, and the trial burden was acceptable.

CONCLUSIONS

Physiotherapist-DART agreement of 78%, with no adverse triage decisions and high patient satisfaction, was sufficient to conclude DART had the potential to improve the musculoskeletal pathway. Study validity was enhanced by the recruitment of real-world patients and using an integrated knowledge translation approach. Completion of a context-specific consensus process is recommended to provide definitive definitions of safety criteria, range of appropriateness, noninferiority margin, and sample size. This pilot demonstrated an adequately powered definitive trial is feasible, which would provide evidence of DART safety and efficacy, ultimately informing potential for DART implementation.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04904029; http://clinicaltrials.gov/ct2/show/NCT04904029.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/31541.

Can artificial intelligence models serve as patient information consultants in orthodontics?

BACKGROUND

To evaluate the accuracy, reliability, quality, and readability of responses generated by ChatGPT-3.5, ChatGPT-4, Gemini, and Copilot in relation to orthodontic clear aligners.

METHODS

Frequently asked questions by patients/laypersons about clear aligners on websites were identified using the Google search tool and these questions were posed to ChatGPT-3.5, ChatGPT-4, Gemini, and Copilot AI models. Responses were assessed using a five-point Likert scale for accuracy, the modified DISCERN scale for reliability, the Global Quality Scale (GQS) for quality, and the Flesch Reading Ease Score (FRES) for readability.

RESULTS

ChatGPT-4 responses had the highest mean Likert score (4.5 ± 0.61), followed by Copilot (4.35 ± 0.81), ChatGPT-3.5 (4.15 ± 0.75) and Gemini (4.1 ± 0.72). The difference between the Likert scores of the chatbot models was not statistically significant (p > 0.05). Copilot had a significantly higher modified DISCERN and GQS score compared to both Gemini, ChatGPT-4 and ChatGPT-3.5 (p < 0.05). Gemini's modified DISCERN and GQS score was statistically higher than ChatGPT-3.5 (p < 0.05). Gemini also had a significantly higher FRES compared to both ChatGPT-4, Copilot and ChatGPT-3.5 (p < 0.05). The mean FRES was 38.39 ± 11.56 for ChatGPT-3.5, 43.88 ± 10.13 for ChatGPT-4 and 41.72 ± 10.74 for Copilot, indicating that the responses were difficult to read according to the reading level. The mean FRES for Gemini is 54.12 ± 10.27, indicating that Gemini's responses are more readable than other chatbots.

CONCLUSIONS

All chatbot models provided generally accurate, moderate reliable and moderate to good quality answers to questions about the clear aligners. Furthermore, the readability of the responses was difficult. ChatGPT, Gemini and Copilot have significant potential as patient information tools in orthodontics, however, to be fully effective they need to be supplemented with more evidence-based information and improved readability.

Perceptions of the Impact of Artificial Intelligence among Internal Medicine Physicians as a Step in Social Responsibility Implementation: A Cross-Sectional Study

Artificial Intelligence (AI) has emerged as an essential tool in healthcare for optimizing healthcare delivery and improving patient outcomes. This study is motivated by using AI in healthcare as a step for social responsibility implementation. The research aimed to investigate the attitudes of healthcare professionals on this issue, and it assessed physicians' opinions regarding their perceptions of AI and their intention to use and implement AI tools in their activity. An electronic survey was proposed during February-June 2024 to a sample of healthcare professionals (309 were admitted into the study, 62 males and 247 females, with a mean age of 42). The results of the survey highlighted both groups' excellent perceptions of AI and the low perceived knowledge of AI, which arises from more technical questions. The use of AI in healthcare represents a step for social responsibility implementation; it is an unstoppable process, and stakeholders should take into consideration investing more in monitoring and training activities.

Structure, governance and delivery of specialist training programs in periodontology and implant dentistry

AIM

To update the competences and learning outcomes and their evaluation, educational methods and education quality assurance for the training of contemporary specialists in periodontology, including the impact of the 2018 Classification of Periodontal and Peri-implant Diseases and Conditions (2018 Classification hereafter) and the European Federation of Periodontology (EFP) Clinical Practice Guidelines (CPGs).

METHODS

Evidence was gathered through scientific databases and by searching for European policies on higher education. In addition, two surveys were designed and sent to program directors and graduates.

RESULTS

Program directors reported that curricula were periodically adapted to incorporate advances in diagnosis, classification, treatment guidelines and clinical techniques, including the 2018 Classification and the EFP CPGs. Graduates evaluated their overall training positively, although satisfaction was limited for training in mucogingival and surgical procedures related to dental implants. Traditional educational methods, such as didactic lectures, are still commonly employed, but they are now often associated with more interactive methods such as case-based seminars and problem-based and simulation-based learning. The evaluation of competences/learning outcomes should employ multiple methods of assessment.

CONCLUSION

An update of competences and learning outcomes of specialist training in periodontology is proposed, including knowledge and practical application of the 2018 Classification and CPGs. Harmonizing specialist training in periodontology is a critical issue at the European level.

Comparison of the Efficacy of Artificial Intelligence-Powered Software in Crown Design: An In Vitro Study

INTRODUCTION AND AIMS

Artificial intelligence (AI) has been adopted in the field of dental restoration. This study aimed to evaluate the time efficiency and morphological accuracy of crowns designed by two AI-powered software programs in comparison with conventional computer-aided design software.

METHODS

A total of 33 clinically adapted posterior crowns were involved in the standard group. AI Automate (AA) and AI Dentbird Crown (AD) used two AI-powered design software programs, while the computer-aided experienced and computer-aided novice employed the Exocad DentalCAD software. Time efficiency between the AI-powered groups and computer-aided groups was evaluated by assessing the elapsed time. Morphological accuracy was assessed by means of three-dimensional geometric calculations, with the root-mean-square error compared against the standard group. Statistical analysis was conducted via the Kruskal-Wallis test (α = 0.05).

RESULTS

The time efficiency of the AI-powered groups was significantly higher than that of the computer-aided groups (P < .01). Moreover, the working time for both AA and AD groups was only one-quarter of that for the computer-aided novice group. Four groups significantly differed in morphological accuracy for occlusal and distal surfaces (P < .05). The AD group performed lower accuracy than the other three groups on the occlusal surfaces (P < .001) and the computer-aided experienced group was superior to the AA group in terms of accuracy on the distal surfaces (P = .029). However, morphological accuracy showed no significant difference among the four groups for mesial surfaces and margin lines (P > .05).

CONCLUSION

AI-powered software enhanced the efficiency of crown design but failed to excel at morphological accuracy compared with experienced technicians using computer-aided software. AI-powered software requires further research and extensive deep learning to improve the morphological accuracy and stability of the crown design.

Doctor simulator: Delta-Age-Sex-AdaIn enhancing bone age assessment through AdaIn style transfer

BACKGROUND

Bone age assessment assists physicians in evaluating the growth and development of children. However, deep learning methods for bone age estimation do not currently incorporate differential features obtained through comparisons with other bone atlases.

OBJECTIVE

To propose a more accurate method, Delta-Age-Sex-AdaIn (DASA-net), for bone age assessment, this paper combines age and sex distribution through adaptive instance normalization (AdaIN) and style transfer, simulating the process of visually comparing hand images with a standard bone atlas to determine bone age.

MATERIALS AND METHODS

The proposed Delta-Age-Sex-AdaIn (DASA-net) consists of four modules: BoneEncoder, Binary code distribution, Delta-Age-Sex-AdaIn, and AgeDecoder. It is compared with state-of-the-art methods on both a public Radiological Society of North America (RSNA) pediatric bone age prediction dataset (14,236 hand radiographs, ranging from 1 to 228 months) and a private bone age prediction dataset from Zigong Fourth People's Hospital (474 hand radiographs, ranging from 12 to 218 months, 268 male). Ablation experiments were designed to demonstrate the necessity of incorporating age distribution and sex distribution.

RESULTS

The DASA-net model achieved a lower mean absolute deviation (MAD) of 3.52 months on the RSNA dataset, outperforming other methods such as BoneXpert, Deeplasia, BoNet, and other deep learning based methods. On the private dataset, the DASA-net model obtained a MAD of 3.82 months, which is also superior to other methods.

CONCLUSION

The proposed DASA-net model aided the model's learning of the distinctive characteristics of hand bones of various ages and both sexes by integrating age and sex distribution into style transfer.

Machine-learning-assisted high-throughput identification of potent and stable neutralizing antibodies against all four dengue virus serotypes

Several computational methods have been developed to identify neutralizing antibodies (NAbs) covering four dengue virus serotypes (DENV-1 to DENV-4); however, limitations of the dataset and the resulting performance remain. Here, we developed a new computational framework to predict potent and stable NAbs against DENV-1 to DENV-4 using only antibody (CDR-H3) and epitope sequences as input. Specifically, our proposed computational framework employed sequence-based ML and molecular dynamic simulation (MD) methods to achieve more accurate identification. First, we built a novel dataset (n = 1108) by compiling the interactions of CDR-H3 and epitope sequences with the half maximum inhibitory concentration (IC50) values, which represent neutralizing activities. Second, we achieved an accurately predictive ML model that showed high AUC values of 0.879 and 0.885 by tenfold cross-validation and independent tests, respectively. Finally, our computational framework could be applied to filter approximately 2.5 million unseen antibodies into two final candidates that showed strong and stable binding to all four serotypes. In addition, the most potent and stable candidate (1B3B9_V21) was evaluated for its development potential as a therapeutic agent by molecular docking and MD simulations. This study provides an antibody computational approach to facilitate the high-throughput identification of NAbs and accelerate the development of therapeutic antibodies.

From Organ-on-a-Chip to Human-on-a-Chip: A Review of Research Progress and Latest Applications

Organ-on-a-Chip (OOC) technology, which emulates the physiological environment and functionality of human organs on a microfluidic chip, is undergoing significant technological advancements. Despite its rapid evolution, this technology is also facing notable challenges, such as the lack of vascularization, the development of multiorgan-on-a-chip systems, and the replication of the human body on a single chip. The progress of microfluidic technology has played a crucial role in steering OOC toward mimicking the human microenvironment, including vascularization, microenvironment replication, and the development of multiorgan microphysiological systems. Additionally, advancements in detection, analysis, and organoid imaging technologies have enhanced the functionality and efficiency of Organs-on-Chips (OOCs). In particular, the integration of artificial intelligence has revolutionized organoid imaging, significantly enhancing high-throughput drug screening. Consequently, this review covers the research progress of OOC toward Human-on-a-chip, the integration of sensors in OOCs, and the latest applications of organoid imaging technologies in the biomedical field.

Human factors considerations for the context-aware design of adaptive autonomous teammates

Despite the gains in performance that AI can bring to human-AI teams, they also present them with new challenges, such as the decline in human ability to respond to AI failures as the AI becomes more autonomous. This challenge is particularly dangerous in human-AI teams, where the AI holds a unique role in the team's success. Thus, it is imperative that researchers find solutions for designing AI team-mates that consider their human team-mates' needs in their adaptation logic. This study explores adaptive autonomy as a solution to overcoming these challenges. We conducted twelve contextual inquiries with professionals in two teaming contexts in order to understand how human teammate perceptions can be used to determine optimal autonomy levels for AI team-mates. The results of this study will enable the human factors community to develop AI team-mates that can enhance their team's performance while avoiding the potentially devastating impacts of their failures.

Identification of profiles associated with conversions between the Alzheimer's disease stages, using a machine learning approach

BACKGROUND

The identification of factors involved in the conversion across the different Alzheimer's disease (AD) stages is crucial to prevent or slow the disease progression. We aimed to assess the factors and their combination associated with the conversion across the AD stages, from mild cognitive impairment to dementia, at a mild, moderate or severe stage and to identify profiles associated with earliest/latest conversion across the AD stages.

METHODS

In this study conducted on the real-life MEMORA cohort data collected from January 1, 2013, and December 31, 2019, three cohorts were selected depending on the baseline neurocognitive stage from a consecutive sample of patients attending a memory center, aged between 50 and 90 years old, with a diagnosis of AD during the follow-up, and with at least 2 visits at 6 months to 1 year of interval. A machine learning approach was used to assess the relationship between factors including socio-demographic characteristics, comorbidities and history of diseases, prescription of drugs, and geriatric hospitalizations, and the censored time to conversion from mild cognitive impairment to AD dementia, from the mild stage of dementia to the moderate or severe stages of AD dementia, and from the moderate stage of AD dementia to the severe stage. Profiles of earliest/latest conversion compared to median time to conversion across stages were identified. The median time to conversion was estimated with a Kaplan-Meier estimator.

RESULTS

Overall, 2891 patients were included (mean age 77±9 years old, 65% women). The median time of follow-up was 28 months for mild cognitive impairment (MCI) patients, 33 months for mild AD dementia and 30 months for moderate AD dementia. Among the 1264 patients at MCI stage, 61% converted to AD dementia (median time to conversion: 25 months). Among the 1142 patients with mild AD dementia, 59% converted to moderate/severe stage (median time: 23 months) and among the 1332 patients with moderate AD dementia, 23% converted to severe stage (Q3 time to conversion: 22 months). Among the studied factors, cardiovascular comorbidities, anxiety, social isolation, osteoporosis, and hearing disorders were identified as being associated with earlier conversion across stages. Symptomatic treatment i.e. cholinesterase inhibitors for AD was associated with later conversion from mild stage of dementia to moderate/severe stages.

CONCLUSION

This study based on a machine learning approach allowed to identify potentially modifiable factors associated with conversion across AD stages for which timely interventions may be implemented to delay disease progression.

Histopathological Alterations in Nilaparvata lugens (Hemiptera: Delphacidae) after Exposure to Cordyceps javanica

The brown planthopper (BPH), Nilaparvata lugens (Stål, 1854), is a pest of rice plants worldwide. Cordyceps javanica is a destructive entomopathogenic fungus known to attack leafhoppers or BPHs specifically. Live adult BPH samples were inoculated with isolated C. javanica PSUC002, and their interaction was morpho-histologically examined from 0 to 120 h post-inoculation (pi). We observed that the mortality of BPH continuously increased until 120 h pi (Day 5). Tissue alterations in the host were examined after infection using morphological and histological methods, including the Grocott Methenamine Silver stain test (GMS). Filamentous fungi were first found on the external integument at 12 h pi, and fungal conidia attached to the integument at 24 h pi. However, the initial degeneration of BPHs was identified by histology at 6 h pi especially in the integument and adipose tissue. We identified the degeneration and loss of integument and adipose tissue of infected BPHs at 12 h pi, and their necrosis was completed at 96 h pi. The enzymatic index of the sampled fungi (chitinase and protease) peaked at 7 days of incubation. This study demonstrated that C. javanica PSUC002 is useful to control the BPHs as an eco-friendly practice and will possibly be applied in agriculture.

Radiology and multi-scale data integration for precision oncology

In this Perspective paper we explore the potential of integrating radiological imaging with other data types, a critical yet underdeveloped area in comparison to the fusion of other multi-omic data. Radiological images provide a comprehensive, three-dimensional view of cancer, capturing features that would be missed by biopsies or other data modalities. This paper explores the complexities and challenges of incorporating medical imaging into data integration models, in the context of precision oncology. We present the different categories of imaging-omics integration and discuss recent progress, highlighting the opportunities that arise from bringing together spatial data on different scales.

A data-centric machine learning approach to improve prediction of glioma grades using low-imbalance TCGA data

Accurate prediction and grading of gliomas play a crucial role in evaluating brain tumor progression, assessing overall prognosis, and treatment planning. In addition to neuroimaging techniques, identifying molecular biomarkers that can guide the diagnosis, prognosis and prediction of the response to therapy has aroused the interest of researchers in their use together with machine learning and deep learning models. Most of the research in this field has been model-centric, meaning it has been based on finding better performing algorithms. However, in practice, improving data quality can result in a better model. This study investigates a data-centric machine learning approach to determine their potential benefits in predicting glioma grades. We report six performance metrics to provide a complete picture of model performance. Experimental results indicate that standardization and oversizing the minority class increase the prediction performance of four popular machine learning models and two classifier ensembles applied on a low-imbalanced data set consisting of clinical factors and molecular biomarkers. The experiments also show that the two classifier ensembles significantly outperform three of the four standard prediction models. Furthermore, we conduct a comprehensive descriptive analysis of the glioma data set to identify relevant statistical characteristics and discover the most informative attributes using four feature ranking algorithms.

Human brain organoids for understanding substance use disorders

Substance use disorders (SUDs) are complex mental health conditions involving a problematic pattern of substance use. Challenges remain in understanding their neural mechanisms, which are likely to lead to improved SUD treatments. Human brain organoids, brain-like 3D in vitro cultures derived from human stem cells, show unique potential in recapitulating the response of a developing human brain to substances. Here, we review the recent progress in understanding SUDs using human brain organoid models focusing on neurodevelopmental perspectives. We first summarize the background of SUDs in humans. Moreover, we introduce the development of various human brain organoid models and then discuss current progress and findings underlying the abuse of substances like nicotine, alcohol, and other addictive drugs using organoid models. Furthermore, we review efforts to develop organ chips and microphysiological systems to engineer better human brain organoids for advancing SUD studies. Lastly, we conclude by elaborating on the current challenges and future directions of SUD studies using human brain organoids.

CATM: A Multi-Feature-Based Cross-Scale Attentional Convolutional EEG Emotion Recognition Model

Aiming at the problem that existing emotion recognition methods fail to make full use of the information in the time, frequency, and spatial domains in the EEG signals, which leads to the low accuracy of EEG emotion classification, this paper proposes a multi-feature, multi-frequency band-based cross-scale attention convolutional model (CATM). The model is mainly composed of a cross-scale attention module, a frequency-space attention module, a feature transition module, a temporal feature extraction module, and a depth classification module. First, the cross-scale attentional convolution module extracts spatial features at different scales for the preprocessed EEG signals; then, the frequency-space attention module assigns higher weights to important channels and spatial locations; next, the temporal feature extraction module extracts temporal features of the EEG signals; and, finally, the depth classification module categorizes the EEG signals into emotions. We evaluated the proposed method on the DEAP dataset with accuracies of 99.70% and 99.74% in the valence and arousal binary classification experiments, respectively; the accuracy in the valence-arousal four-classification experiment was 97.27%. In addition, considering the application of fewer channels, we also conducted 5-channel experiments, and the binary classification accuracies of valence and arousal were 97.96% and 98.11%, respectively. The valence-arousal four-classification accuracy was 92.86%. The experimental results show that the method proposed in this paper exhibits better results compared to other recent methods, and also achieves better results in few-channel experiments.

Navigating the Metaverse: A New Virtual Tool with Promising Real Benefits for Breast Cancer Patients

BC, affecting both women and men, is a complex disease where early diagnosis plays a crucial role in successful treatment and enhances patient survival rates. The Metaverse, a virtual world, may offer new, personalized approaches to diagnosing and treating BC. Although Artificial Intelligence (AI) is still in its early stages, its rapid advancement indicates potential applications within the healthcare sector, including consolidating patient information in one accessible location. This could provide physicians with more comprehensive insights into disease details. Leveraging the Metaverse could facilitate clinical data analysis and improve the precision of diagnosis, potentially allowing for more tailored treatments for BC patients. However, while this article highlights the possible transformative impacts of virtual technologies on BC treatment, it is important to approach these developments with cautious optimism, recognizing the need for further research and validation to ensure enhanced patient care with greater accuracy and efficiency.

GA-GBLUP: leveraging the genetic algorithm to improve the predictability of genomic selection

Genomic selection (GS) has emerged as an effective technology to accelerate crop hybrid breeding by enabling early selection prior to phenotype collection. Genomic best linear unbiased prediction (GBLUP) is a robust method that has been routinely used in GS breeding programs. However, GBLUP assumes that markers contribute equally to the total genetic variance, which may not be the case. In this study, we developed a novel GS method called GA-GBLUP that leverages the genetic algorithm (GA) to select markers related to the target trait. We defined four fitness functions for optimization, including AIC, BIC, R2, and HAT, to improve the predictability and bin adjacent markers based on the principle of linkage disequilibrium to reduce model dimension. The results demonstrate that the GA-GBLUP model, equipped with R2 and HAT fitness function, produces much higher predictability than GBLUP for most traits in rice and maize datasets, particularly for traits with low heritability. Moreover, we have developed a user-friendly R package, GAGBLUP, for GS, and the package is freely available on CRAN (https://CRAN.R-project.org/package=GAGBLUP).

Multimodal data integration for oncology in the era of deep neural networks: a review

Cancer research encompasses data across various scales, modalities, and resolutions, from screening and diagnostic imaging to digitized histopathology slides to various types of molecular data and clinical records. The integration of these diverse data types for personalized cancer care and predictive modeling holds the promise of enhancing the accuracy and reliability of cancer screening, diagnosis, and treatment. Traditional analytical methods, which often focus on isolated or unimodal information, fall short of capturing the complex and heterogeneous nature of cancer data. The advent of deep neural networks has spurred the development of sophisticated multimodal data fusion techniques capable of extracting and synthesizing information from disparate sources. Among these, Graph Neural Networks (GNNs) and Transformers have emerged as powerful tools for multimodal learning, demonstrating significant success. This review presents the foundational principles of multimodal learning including oncology data modalities, taxonomy of multimodal learning, and fusion strategies. We delve into the recent advancements in GNNs and Transformers for the fusion of multimodal data in oncology, spotlighting key studies and their pivotal findings. We discuss the unique challenges of multimodal learning, such as data heterogeneity and integration complexities, alongside the opportunities it presents for a more nuanced and comprehensive understanding of cancer. Finally, we present some of the latest comprehensive multimodal pan-cancer data sources. By surveying the landscape of multimodal data integration in oncology, our goal is to underline the transformative potential of multimodal GNNs and Transformers. Through technological advancements and the methodological innovations presented in this review, we aim to chart a course for future research in this promising field. This review may be the first that highlights the current state of multimodal modeling applications in cancer using GNNs and transformers, presents comprehensive multimodal oncology data sources, and sets the stage for multimodal evolution, encouraging further exploration and development in personalized cancer care.

Impact of Large Language Models on Medical Education and Teaching Adaptations

Unlabelled

This viewpoint article explores the transformative role of large language models (LLMs) in the field of medical education, highlighting their potential to enhance teaching quality, promote personalized learning paths, strengthen clinical skills training, optimize teaching assessment processes, boost the efficiency of medical research, and support continuing medical education. However, the use of LLMs entails certain challenges, such as questions regarding the accuracy of information, the risk of overreliance on technology, a lack of emotional recognition capabilities, and concerns related to ethics, privacy, and data security. This article emphasizes that to maximize the potential of LLMs and overcome these challenges, educators must exhibit leadership in medical education, adjust their teaching strategies flexibly, cultivate students' critical thinking, and emphasize the importance of practical experience, thus ensuring that students can use LLMs correctly and effectively. By adopting such a comprehensive and balanced approach, educators can train health care professionals who are proficient in the use of advanced technologies and who exhibit solid professional ethics and practical skills, thus laying a strong foundation for these professionals to overcome future challenges in the health care sector.

A hybrid recommendation algorithm based on user nearest neighbor model

In the realm of e-commerce, personalized recommendations are a crucial component in enhancing user experience and optimizing sales efficiency. To address the inherent sparsity challenge prevalent in collaborative filtering algorithms within personalized recommendation systems, we propose a novel hybrid e-commerce recommendation algorithm based on the User-Nearest-Neighbor model. By integrating the user nearest neighbor model with other recommendation algorithms, this approach effectively mitigates data sparsity and facilitates a more nuanced understanding of the user-product relationship, consequently elevating recommendation quality and enhancing user experience. Taking into account considerations such as data scale and recommendation performance, we conducted experiments utilizing the Spark distributed platform. Empirical findings demonstrate the superiority of our hybrid algorithm over standalone collaborative filtering algorithms across various recommendation indicators.

Enhancing kiwifruit flower pollination detection through frequency domain feature fusion: a novel approach to agricultural monitoring

The pollination process of kiwifruit flowers plays a crucial role in kiwifruit yield. Achieving accurate and rapid identification of the four stages of kiwifruit flowers is essential for enhancing pollination efficiency. In this study, to improve the efficiency of kiwifruit pollination, we propose a novel full-stage kiwifruit flower pollination detection algorithm named KIWI-YOLO, based on the fusion of frequency-domain features. Our algorithm leverages frequency-domain and spatial-domain information to improve recognition of contour-detailed features and integrates decision-making with contextual information. Additionally, we incorporate the Bi-Level Routing Attention (BRA) mechanism with C3 to enhance the algorithm's focus on critical areas, resulting in accurate, lightweight, and fast detection. The algorithm achieves a m A P 0.5 of 91.6% with only 1.8M parameters, the AP of the Female class and the Male class reaches 95% and 93.5%, which is an improvement of 3.8%, 1.2%, and 6.2% compared with the original algorithm. Furthermore, the Recall and F1-score of the algorithm are enhanced by 5.5% and 3.1%, respectively. Moreover, our model demonstrates significant advantages in detection speed, taking only 0.016s to process an image. The experimental results show that the algorithmic model proposed in this study can better assist the pollination of kiwifruit in the process of precision agriculture production and help the development of the kiwifruit industry.

Physical therapists' perceptions and attitudes towards artificial intelligence in healthcare and rehabilitation: A qualitative study

BACKGROUND

Artificial intelligence (AI) is being introduced to rehabilitation practices, and it can optimize the patient's outcome through their ability to design personalized care strategies and interventions.

OBJECTIVES

To understand the attitudes and perceptions of physical therapy professionals on the use of AI in rehabilitation in regard to treatment planning, diagnosis, outcome prediction, and advantages and disadvantages.

DESIGN AND METHODS

This paper followed an exploratory, qualitative research design. Semi-structured, one-to-one interviews were conducted with participants of different experience levels and specialties in physical therapy. Results were evaluated using thematic analysis.

RESULTS

Four themes were identified: (i) perceptions of AI and its applications in healthcare services, (ii) impact on the workforce (iii) considerations around implementing AI within rehabilitation and (iv) AI, and the fast-approaching future. Participants shared views on the potential impact of AI on rehabilitation practices, such as aiding the decision-making process, saving time and effort of both the therapist and patients. Participants have stressed on potential pitfalls that still need to be considered, such as patient data privacy, potential loss of patient-healthcare practitioner relationship, ethical concerns regarding overreliance on these applications and how that might hinder effective patient care.

CONCLUSION

The findings add to the literature about physical therapists' understanding regarding the use of AI in patient care. Several concerns were raised to the adoption of AI, including concerns about patient privacy, and ethical concerns. Based on the study findings, researchers emphasize the importance of establishing guidelines when incorporating AI in rehabilitation to improve the therapist's knowledge and skills.